metadata
license: apache-2.0
language:
- de
- en
- it
- fr
- pt
- nl
- ru
- ar
- es
tags:
- spectrum
- TensorBlock
- GGUF
base_model: VAGOsolutions/SauerkrautLM-Nemo-12b-Instruct
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
VAGOsolutions/SauerkrautLM-Nemo-12b-Instruct - GGUF
This repo contains GGUF format model files for VAGOsolutions/SauerkrautLM-Nemo-12b-Instruct.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
<s>[INST] {system_prompt}
{prompt}[/INST]
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| SauerkrautLM-Nemo-12b-Instruct-Q2_K.gguf | Q2_K | 4.462 GB | smallest, significant quality loss - not recommended for most purposes |
| SauerkrautLM-Nemo-12b-Instruct-Q3_K_S.gguf | Q3_K_S | 5.154 GB | very small, high quality loss |
| SauerkrautLM-Nemo-12b-Instruct-Q3_K_M.gguf | Q3_K_M | 5.665 GB | very small, high quality loss |
| SauerkrautLM-Nemo-12b-Instruct-Q3_K_L.gguf | Q3_K_L | 6.111 GB | small, substantial quality loss |
| SauerkrautLM-Nemo-12b-Instruct-Q4_0.gguf | Q4_0 | 6.586 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| SauerkrautLM-Nemo-12b-Instruct-Q4_K_S.gguf | Q4_K_S | 6.631 GB | small, greater quality loss |
| SauerkrautLM-Nemo-12b-Instruct-Q4_K_M.gguf | Q4_K_M | 6.964 GB | medium, balanced quality - recommended |
| SauerkrautLM-Nemo-12b-Instruct-Q5_0.gguf | Q5_0 | 7.934 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| SauerkrautLM-Nemo-12b-Instruct-Q5_K_S.gguf | Q5_K_S | 7.934 GB | large, low quality loss - recommended |
| SauerkrautLM-Nemo-12b-Instruct-Q5_K_M.gguf | Q5_K_M | 8.128 GB | large, very low quality loss - recommended |
| SauerkrautLM-Nemo-12b-Instruct-Q6_K.gguf | Q6_K | 9.366 GB | very large, extremely low quality loss |
| SauerkrautLM-Nemo-12b-Instruct-Q8_0.gguf | Q8_0 | 12.128 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/SauerkrautLM-Nemo-12b-Instruct-GGUF --include "SauerkrautLM-Nemo-12b-Instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:
huggingface-cli download tensorblock/SauerkrautLM-Nemo-12b-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'